Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16d10bf9a111161de20e15d969d0718256939f6c381d64394c50b2255908991
+oid sha256:d98f52ea9e3b4f5493caa758d4f5fde320b07d26e631a62d06b30efdb375999a
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddea746290e791019360e6635a4efd9a761a0c5be7fc82ebae738ac75ed8e49
+oid sha256:ea55249602bec4a7f78154c7173c8d40a8529f23d77824a36381cae980615f5a
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9517b7ce59c47365939baf2f50e6bfd58d4414b9c61ed194de990178b59d75
+oid sha256:9418a68e5819dc4b84034984f04774a6cc7da23a601f4d1f77e1c7bf288f18ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016418204505155316,
+  "epoch": 0.0024627306757732973,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 10.3697,
       "step": 50
+    },
+    {
+      "epoch": 0.0016746568595258423,
+      "grad_norm": 0.042693495750427246,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.3793,
+      "step": 51
+    },
+    {
+      "epoch": 0.001707493268536153,
+      "grad_norm": 0.045006535947322845,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3675,
+      "step": 52
+    },
+    {
+      "epoch": 0.0017403296775464635,
+      "grad_norm": 0.04501199349761009,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3753,
+      "step": 53
+    },
+    {
+      "epoch": 0.0017731660865567742,
+      "grad_norm": 0.04330871254205704,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.374,
+      "step": 54
+    },
+    {
+      "epoch": 0.0017731660865567742,
+      "eval_loss": 10.37214469909668,
+      "eval_runtime": 170.1851,
+      "eval_samples_per_second": 150.695,
+      "eval_steps_per_second": 18.838,
+      "step": 54
+    },
+    {
+      "epoch": 0.0018060024955670847,
+      "grad_norm": 0.05513521283864975,
+      "learning_rate": 5e-05,
+      "loss": 10.367,
+      "step": 55
+    },
+    {
+      "epoch": 0.0018388389045773954,
+      "grad_norm": 0.048482492566108704,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3717,
+      "step": 56
+    },
+    {
+      "epoch": 0.001871675313587706,
+      "grad_norm": 0.0455101802945137,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3688,
+      "step": 57
+    },
+    {
+      "epoch": 0.0019045117225980166,
+      "grad_norm": 0.04642629623413086,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3778,
+      "step": 58
+    },
+    {
+      "epoch": 0.0019373481316083273,
+      "grad_norm": 0.0608275830745697,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3782,
+      "step": 59
+    },
+    {
+      "epoch": 0.001970184540618638,
+      "grad_norm": 0.049797091633081436,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3706,
+      "step": 60
+    },
+    {
+      "epoch": 0.0020030209496289487,
+      "grad_norm": 0.0518428236246109,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.3705,
+      "step": 61
+    },
+    {
+      "epoch": 0.002035857358639259,
+      "grad_norm": 0.04151507094502449,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3754,
+      "step": 62
+    },
+    {
+      "epoch": 0.0020686937676495697,
+      "grad_norm": 0.047984637320041656,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3595,
+      "step": 63
+    },
+    {
+      "epoch": 0.0020686937676495697,
+      "eval_loss": 10.37141227722168,
+      "eval_runtime": 170.6032,
+      "eval_samples_per_second": 150.325,
+      "eval_steps_per_second": 18.792,
+      "step": 63
+    },
+    {
+      "epoch": 0.0021015301766598806,
+      "grad_norm": 0.049031127244234085,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3674,
+      "step": 64
+    },
+    {
+      "epoch": 0.002134366585670191,
+      "grad_norm": 0.051563944667577744,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.376,
+      "step": 65
+    },
+    {
+      "epoch": 0.0021672029946805016,
+      "grad_norm": 0.04762021079659462,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3799,
+      "step": 66
+    },
+    {
+      "epoch": 0.0022000394036908125,
+      "grad_norm": 0.06098484992980957,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.3745,
+      "step": 67
+    },
+    {
+      "epoch": 0.002232875812701123,
+      "grad_norm": 0.04760457202792168,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3699,
+      "step": 68
+    },
+    {
+      "epoch": 0.0022657122217114335,
+      "grad_norm": 0.05251610651612282,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3793,
+      "step": 69
+    },
+    {
+      "epoch": 0.0022985486307217444,
+      "grad_norm": 0.05606340244412422,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3652,
+      "step": 70
+    },
+    {
+      "epoch": 0.002331385039732055,
+      "grad_norm": 0.04817664250731468,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.374,
+      "step": 71
+    },
+    {
+      "epoch": 0.0023642214487423654,
+      "grad_norm": 0.047362156212329865,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3679,
+      "step": 72
+    },
+    {
+      "epoch": 0.0023642214487423654,
+      "eval_loss": 10.370889663696289,
+      "eval_runtime": 170.6022,
+      "eval_samples_per_second": 150.326,
+      "eval_steps_per_second": 18.792,
+      "step": 72
+    },
+    {
+      "epoch": 0.0023970578577526764,
+      "grad_norm": 0.05063464865088463,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3752,
+      "step": 73
+    },
+    {
+      "epoch": 0.002429894266762987,
+      "grad_norm": 0.05633007362484932,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3643,
+      "step": 74
+    },
+    {
+      "epoch": 0.0024627306757732973,
+      "grad_norm": 0.06308276206254959,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3707,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2615122329600.0,
+  "total_flos": 3922683494400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null